Constant time O(1) bilateral filtering

By Fatih Murat Porikli. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

372 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b8b4eeddaa5b8bca921d1dc2f9e1ad0a3edbfae0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Real-time O(1) bilateral filtering (2009, methodology): “(a) is a synthetic 8-bit grayscale image with resolution 512 × 384, (b) and (c) are bilateral filtered results using Porikli’s method [1] and our method with the same parameter setting, respectively.”
Constant Time Weighted Median Filtering for Stereo Matching and Beyond (2013, background): “The weighted median filter inherits some desired properties from both median filtering and edge-aware averaging filtering (the guided filter).”
Monocular Depth Estimation Using Neural Regression Forest (2016, methodology): “We use an off-theshelf linear-time implementation for the bi-lateral filtering [19].”
A non-local cost aggregation method for stereo matching (2012, methodology): “A number of approximation methods have been developed to accelerate the bilateral filter, including Paris and Durand’s fast bilateral filter [12], Porikli’s O(1) bilateral filter [17] and Yang’s real-time bilateral filters [25, 26].”
Rolling Guidance Filter (2014, methodology): “Since acceleration of edge-aware filtering was well studied, many tools are available [8,19,28,22,33,32,2,1,11,12,13].”
Fast High‐Dimensional Filtering Using the Permutohedral Lattice (2010, background): “The work of Durand and Dorsey [DD02] was independently extended by Porikli [Por08] who observed that the FFTs were unnecessary, and used faster integral-image based methods to blur each intensity level, thus producing integral histograms.”
Visual Tracking via Locality Sensitive Histograms (2013, methodology): “They are computed at each pixel location, and have been proved to be very useful for many tasks like the bilateral filtering [25, 16], median filtering [25, 12] and tracking [15, 1].”
Guided Image Filtering (2010, methodology): “Porikli’s method [18] has apparent quantization artifacts even when B ¼ 32 .”